Description:

OpenAI’s Hardware organization develops silicon and system-level solutions for advanced AI workloads.
The team is responsible for building next-generation AI-native silicon and creating custom design tools and methodologies.
As a software engineer on the Scaling team, you will optimize the low-level stack for computation and data movement across supercomputing clusters.
Your responsibilities include designing high-performance runtimes, building custom kernels, and contributing to compiler infrastructure.
You will develop scalable simulation systems to validate and optimize distributed training workloads.
The role involves creating ergonomic developer APIs and efficient runtime systems while balancing ease of use with performance.
This position is based in San Francisco, CA, with a hybrid work model (3 days/week in-office) and relocation assistance available.

Requirements:

You should have a deep curiosity for large-scale systems and a desire to improve their speed, simplicity, and reliability.
Proficiency in systems programming languages such as Rust and C++, as well as scripting languages like Python, is required.
Experience in areas such as compiler development, kernel authoring, accelerator programming, runtime systems, distributed systems, or high-performance simulation is necessary.
You should be excited to work in a fast-paced, collaborative environment with evolving hardware and ML system demands.
A commitment to engineering excellence, technical leadership, and thoughtful system design is essential.

OpenAI offers a hybrid work model, allowing flexibility in work arrangements.
Relocation assistance is provided for candidates moving to San Francisco, CA.
The company is committed to diversity and inclusion, ensuring equal opportunity for all applicants.
OpenAI values the perspectives and experiences of its employees, fostering a collaborative and innovative work environment.

Skills